To see the other types of publications on this topic, follow the link: Deeplearning.
Journal articles on the topic 'Deeplearning'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Deeplearning.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Pulaparthi, Naga MahaLakshmi, Madhulika Dabbiru, Charishma Penkey, and Dr Nrusimhadri Naveen. "Brain Stroke Detection Using DeepLearning." International Journal of Research Publication and Reviews 4, no. 4 (April 2023): 2468–73. http://dx.doi.org/10.55248/gengpi.4.423.35996.
Full text
2
Verma, Pratibha, Vineet Kumar Awasthi, and Sanat Kumar Sahu. "A Novel Design of Classification of Coronary Artery Disease Using Deep Learning and Data Mining Algorithms." Revue d'Intelligence Artificielle 35, no. 3 (June 30, 2021): 209–15. http://dx.doi.org/10.18280/ria.350304.
Full textAbstract:
Data mining techniques are included with Ensemble learning and deep learning for the classification. The methods used for classification are, Single C5.0 Tree (C5.0), Classification and Regression Tree (CART), kernel-based Support Vector Machine (SVM) with linear kernel, ensemble (CART, SVM, C5.0), Neural Network-based Fit single-hidden-layer neural network (NN), Neural Networks with Principal Component Analysis (PCA-NN), deep learning-based H2OBinomialModel-Deeplearning (HBM-DNN) and Enhanced H2OBinomialModel-Deeplearning (EHBM-DNN). In this study, experiments were conducted on pre-processed datasets using R programming and 10-fold cross-validation technique. The findings show that the ensemble model (CART, SVM and C5.0) and EHBM-DNN are more accurate for classification, compared with other methods.
3
A. J., Anju, and J. E. Judith. "Optimized Deeplearning Algorithm for Software Defects Prediction." International Journal on Recent and Innovation Trends in Computing and Communication 11, no. 9s (August 31, 2023): 173–88. http://dx.doi.org/10.17762/ijritcc.v11i9s.7409.
Full textAbstract:
Accurate software defect prediction (SDP) helps to enhance the quality of the software by identifying potential flaws early in the development process. However, existing approaches face challenges in achieving reliable predictions. To address this, a novel approach is proposed that combines a two-tier-deep learning framework. The proposed work includes four major phases:(a) pre-processing, (b) Dimensionality reduction, (c) Feature Extraction and (d) Two-fold deep learning-based SDP. The collected raw data is initially pre-processed using a data cleaning approach (handling null values and missing data) and a Decimal scaling normalisation approach. The dimensions of the pre-processed data are reduced using the newly developed Incremental Covariance Principal Component Analysis (ICPCA), and this approach aids in solving the “curse of dimensionality” issue. Then, onto the dimensionally reduced data, the feature extraction is performed using statistical features (standard deviation, skewness, variance, and kurtosis), Mutual information (MI), and Conditional entropy (CE). From the extracted features, the relevant ones are selected using the new Euclidean Distance with Mean Absolute Deviation (ED-MAD). Finally, the SDP (decision making) is carried out using the optimized Two-Fold Deep Learning Framework (O-TFDLF), which encapsulates the RBFN and optimized MLP, respectively. The weight of MLP is fine-tuned using the new Levy Flight Cat Mouse Optimisation (LCMO) method to improve the model's prediction accuracy. The final detected outcome (forecasting the presence/ absence of defect) is acquired from optimized MLP. The implementation has been performed using the MATLAB software. By using certain performance metrics such as Sensitivity, Accuracy, Precision, Specificity and MSE the proposed model’s performance is compared to that of existing models. The accuracy achieved for the proposed model is 93.37%.
4
Motwani, Nilesh Parmanand, and Soumya S. "Human Activities Detection using DeepLearning Technique- YOLOv8." ITM Web of Conferences 56 (2023): 03003. http://dx.doi.org/10.1051/itmconf/20235603003.
Full textAbstract:
Using a mask during the pandemic has occasionally been crucial and difficult. The use of universal masks can greatly lower and possibly even stop the spread of viruses within communities. So, mask detection has become a very critical task for security agencies in all the buildings, Government offices & other places. With the advent of GPUs, high computing machines, and Deep Convolution Neural Networks (DCCN), automatic Face & Mask Detection is possible by considering the image processing feature of extracting, 3-dimensional shapes from 2- dimensional images. This paper discuss about the YOLOv8 model to confirm its overall applicability, on two datasets namely FDDB & MASK. This helps to examine the behavior of the feature from the Mask dataset, which is intended for COVID-19 Mask Detection alone. Mask is the main dataset in this experiment. Above this, the ImageNet dataset is utilized for pretraining and FDDB (Face Detection Dataset & Benchmarks) datasets for recognizing face of a human being. The precision of models on FDDB is 58.9 % & on MASK dataset is 66.5%.
5
Sherly, S. Irin, J. Sandhiya, S. Priyanga, M. A. Sharon Victoriya, and K. Sorna Ajantha. "Prediction of Cardiovascular Disease using DeepLearning Algorithm." Journal of Cognitive Human-Computer Interaction 5, no. 1 (2023): 20–31. http://dx.doi.org/10.54216/jchci.050102.
Full textAbstract:
The leading cause of death, which affects millions of individuals globally is the cardiovascular disease. Heart problems are a major issue in health care, particularly in the field of cardiology. Due to a number of risk factors, including diabetes, high blood pressure, high cholesterol, an irregular pulse rate, obesity, and smoking, cardiac illness is difficult to detect. Due to these limitations, researchers are now using Data Mining and Deep Learning Algorithms to predict heart related disorders. The Cardio Vascular Disease (CVD) is as complicated as it sounds if left untreated. So, the early prediction of this could save millions of people from silent attacks, myocardial infarction etc. Many machine learning algorithms like Naïve Bayes, K-Nearest Neighbor Algorithm (KNN), Decision Trees (DT), Genetic algorithm (GA) are used for cardiovascular disease prediction using text datasets and their efficiencies tend to differ. Generally, convolutional neural network (CNN) algorithm is mostly used for prediction using images. But our concept is to switch over this and predict heart disease using the CNN algorithm for Cleveland dataset which consists of numerical. In this dataset we consider 14 attributes and used K Nearest Neighbor and CNN algorithm. In terms of accuracy, CNN beats KNN, proving that deep learning algorithms may support decision-making and prediction-making based on vast volumes of data supplied by the healthcare sector.
6
Li, Xun, Xin Yun, Zhengfan Zhao, Kaibin Zhang, and Xiaohua Wang. "Lightweight Deeplearning Method for Multi-vehicle Object Recognition." Information Technology and Control 51, no. 2 (June 23, 2022): 294–312. http://dx.doi.org/10.5755/j01.itc.51.2.30667.
Full textAbstract:
The recognition method based on deep learning has a large amount of calculation for the changes of different traffic densities in the actual traffic environment. In this paper, an integrated recognition method YOLOv4-L is proposed for reducing computational complexity based on the YOLOv4. The characteristics of multi-lane traffic flow with different flow densities were analyzed for statistical data sets, and k-means++ clustering algorithm was used to optimize the prior frame parameters to improve the matching degree between the prior frame. GhostNet was used to replace CSPDarknet53 of original network structure of YOLOv4 as the feature extraction network. The depthwise separable convolution module was introduced to replace the original 3×3 common convolution in feature extraction network, reduce model parameters and improve detection speed. The network model is further improved both with accuracy and robustness with the help of comprehensive method of Mosaic data enhancement, learning rate cosine annealing and label smoothing. Experimental results show that, Recognition speed is greatly improved at the expense of minimal recognition accuracy reduction: the recognition speed improvement value is 47.81%, 49.15% , 56.06% in detection speed (FPS), respectively in free flow, synchronous flow and blocked flow, the reduction value of accuracy is 2.21%, 0.67%,, 0.05% mAP, respectively.
7
Doroshenko, А. Yu, V. M. Shpyg, and R. V. Kushnirenko. "Deeplearning-based approach to improving numerical weather forecasts." PROBLEMS IN PROGRAMMING, no. 3 (September 2023): 91–98. http://dx.doi.org/10.15407/pp2023.03.091.
Full textAbstract:
This paper briefly describes the history of numerical weather prediction development. The difficulties, which occur in the modelling of atmospheric processes, their nature and possible ways of their mitigation, are described. It also indicates alternative methods of improving the quality of meteorological forecasts. A brief history of deep learning and possible ways of its application to meteorological problems are given. Then, the paper describes the format used to store the 2m temperature forecasts of the COSMO numerical regional model. The proposed neural network architecture enables correcting the forecast errors of the numerical model. We conducted the experiments on the data of eight meteorological stations of the Kyiv region, so we obtained eight trained neural network models. The results showed that the proposed architecture enables obtaining better-quality forecasts in more than 50% of cases. Root-mean-square errors of the resulting forecasts decreased, and it is a widespread skill-score of improved-quality forecasts in meteorological science.
8
Tiku, Johanes Christianto, Wahyu Andi Saputra, and Novian Adi Prasetyo. "Pengembangan Sistem Deteksi Memakai Masker Menggunakan Open CV, Tensorflow dan Keras." JURIKOM (Jurnal Riset Komputer) 9, no. 4 (August 30, 2022): 1183. http://dx.doi.org/10.30865/jurikom.v9i4.4739.
Full textAbstract:
In 2020 the country had contracted the covid 19 virus. The very significant spread made the government have to issue regulations regarding the implementation of health protocols for wearing mask to inhibit the development of the covid 19 virus in the community in real time. By utilizing technological developments in the field of deeplearning and computer vision, this study aims to detect maskon people's faces based on the classification made in the system of wearing maskand not wearing memakai maskers. This study used tensorflow/hard, opencv and deeplearning to perform classification and detection on faces. Based on the results of the confusion matrix test using 100 test data with a group of 50 wearing maskand 50 not wearing memakai maskers, it resulted in 91% Accuracy to detect maskon the faceTRANSLATE with x EnglishArabicHebrewPolishBulgarianHindiPortugueseCatalanHmong DawRomanianChinese SimplifiedHungarianRussianChinese TraditionalIndonesianSlovakCzechItalianSlovenianDanishJapaneseSpanishDutchKlingonSwedishEnglishKoreanThaiEstonianLatvianTurkishFinnishLithuanianUkrainianFrenchMalayUrduGermanMalteseVietnameseGreekNorwegianWelshHaitian CreolePersian // TRANSLATE with COPY THE URL BELOW Back EMBED THE SNIPPET BELOW IN YOUR SITE Enable collaborative features and customize widget: Bing Webmaster PortalBack//
9
Jo and Kim. "NIR Reflection Augmentation for DeepLearning-Based NIR Face Recognition." Symmetry 11, no. 10 (October 3, 2019): 1234. http://dx.doi.org/10.3390/sym11101234.
Full textAbstract:
Face recognition using a near-infrared (NIR) sensor is widely applied to practical applications such as mobile unlocking or access control. However, unlike RGB sensors, few deep learning approaches have studied NIR face recognition. We conducted comparative experiments for the application of deep learning to NIR face recognition. To accomplish this, we gathered five public databases and trained two deep learning architectures. In our experiments, we found that simple architecture could have a competitive performance on the NIR face databases that are mostly composed of frontal face images. Furthermore, we propose a data augmentation method to train the architectures to improve recognition of users who wear glasses. With this augmented training set, the recognition rate for users who wear glasses increased by up to 16%. This result implies that the recognition of those who wear glasses can be overcome using this simple method without constructing an additional training set. Furthermore, the model that uses augmented data has symmetry with those trained with real glasses-wearing data regarding the recognition of people who wear glasses.
10
Sidana, Khushi. "REAL TIME YOGA POSE DETECTION USING DEEPLEARNING: A REVIEW." International Journal of Engineering Applied Sciences and Technology 7, no. 7 (November 1, 2022): 61–65. http://dx.doi.org/10.33564/ijeast.2022.v07i07.011.
Full textAbstract:
With the increase in the number of yoga practitioners every year, the risk of injuries as a result of incorrect yoga postures has also increased. A selftraining model that can evaluate the posture of individuals is the optimal solution for this issue. This objective can be attained with the aid of computer vision and deep learning. A model that can detect theyoga pose performed by an individual, evaluate it in comparison to the pose performed by an expert, and provide the individual with instructive feedback would be an effective solution to this problem. Recently, numerous researchers have conducted experiments on the detection and performance of yoga poses in real time. This paper discusses the methods undertaken in brief and compares the tools and algorithms they used for conducting pose estimation, pose detection as well as pose assessment. Itdiscusses the accuracy, precision, and similarity of pose classification obtained by the researchers and the future scope of the research.
11
Lin, Hong, Suresh Chandra Satapathy, and V. Rajinikanth. "Medical Data Assessment with Traditional, Machine-learning and Deeplearning Techniques." Current Medical Imaging Formerly Current Medical Imaging Reviews 16, no. 10 (January 12, 2021): 1185–86. http://dx.doi.org/10.2174/157340561610210112143516.
Full text
12
Li, Dalin, Talin Haritunians, Emebet Mengesha, Stephan R. Targan, and Dermot McGovern. "151 – Using Deeplearning and Genetic Bigdata to Predict Crohn's Disease." Gastroenterology 156, no. 6 (May 2019): S—35. http://dx.doi.org/10.1016/s0016-5085(19)36864-7.
Full text
13
SERENER, Ali, and Sertan SERTE. "Geographic variation and ethnicity in diabetic retinopathy detection via deeplearning." TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES 28, no. 2 (March 28, 2020): 664–78. http://dx.doi.org/10.3906/elk-1902-131.
Full text
14
Zhang, Zhiyuan, Yan Yan, Zihe Wang, Tao Song, Jianping Yin, Xiyu He, Peiming Guo, and Shaoke Wang. "SDPNet: A Novel DeepLearning Method for Ocean Surface Current Prediction." Journal of Physics: Conference Series 2486, no. 1 (May 1, 2023): 012066. http://dx.doi.org/10.1088/1742-6596/2486/1/012066.
Full textAbstract:
Abstract Ocean surface currents (OSC), abiotic features of the environment, are continuous and directed movements of ocean water. Prediction to OSC is of significant interests in physical oceanography. Recently, deep learning technology has shown feasibility in mining the intrinsic change pattern of marine numerical values, such as SSS, SST and SSHA, but not been applied to OSC prediction yet. In this work, a deep learning method, named skipped dual path network (SDPNet), is proposed for OSC prediction. Specifically, SDPNet has a convolutional neural network (CNN) module with a one-dimensional convolution layer, and a recurrent neural network (RNN) module with a dual-path structure. Each path consists of a stack of three layers of long short-term memory (LSTM) and gated recurrent unit (GRU), respectively. As well, a skipped-connection structure is added in the both paths. It aims to gradually mine the intrinsic change pattern contained in OSC time series data itself. Experiments are conducted on the South China Sea OSC data set in REDOS. SDPNet achieves accuracy 80.83%, 75.9%, 74.9%, 73.9%, 72.58%, 70.35%, 69.93% in predicting the coming 7 days OSC values and directions. It performs better than state-of-the-art machine learning methods, include Artificial Neural Network, Simple RNN, LSTM and GRU.
15
Zhang, Kun, and Koji Yamada. "Multi-Object Detection and Tracking on Mobile Device Based on DeepLearning." Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) 2020 (2020): 2P1—N08. http://dx.doi.org/10.1299/jsmermd.2020.2p1-n08.
Full text
16
Shanthi, Dr A. S. "College Enquiry Chat Bot Using Machine Learning." International Journal for Research in Applied Science and Engineering Technology 11, no. 6 (June 30, 2023): 143–45. http://dx.doi.org/10.22214/ijraset.2023.53538.
Full textAbstract:
Abstract: To develop a college enquiry Chatbot that answers any queries post by students like college details, course-related questions, location of the college, fee structure etc. The College Enquiry Chatbot project is built using Deeplearning, Neural Network with Natural Language Processing that analyze user’s queries and understand the user's message. This System is a web application that provides answers to the query. Any individual just has to query through the bot. The answers are appropriate to what the user queries.
17
Kusuma, S., and J. Divya Udayan. "Analysis on Deep Learning methods for ECG based Cardiovascular Disease prediction." Scalable Computing: Practice and Experience 21, no. 1 (March 19, 2020): 127–36. http://dx.doi.org/10.12694/scpe.v21i1.1640.
Full textAbstract:
The cardiovascular related diseases can however be controlled through earlierdetection as well as risk evaluation and prediction. In this paper the applicationof deep learning methods for CVD diagnosis using ECG is addressed.A detailed Analysis of related articles has been conducted. The results indicatethat convolutional neural networks (CNN) are the most widely used deeplearning technique in the CVD diagnosis. This research paper looks into theadvantages of deep learning approaches that can be brought by developing aframework that can enhance prediction of heart related diseases using ECG.
18
Chen, Taotao, Zhongmin Chen, and Zhixuan Zhou. "Computational Research and Implementation of Prediction of Pork Price Based on Deeplearning." Journal of Physics: Conference Series 1815, no. 1 (February 1, 2021): 012032. http://dx.doi.org/10.1088/1742-6596/1815/1/012032.
Full text
19
Li, Shufei, Lianyu Zheng, Yiwei Wang, and Renjie Zhang. "Reading Aviation Wire Text in Natural Images under Assembly Workshop via Deeplearning." IOP Conference Series: Materials Science and Engineering 563 (August 9, 2019): 042075. http://dx.doi.org/10.1088/1757-899x/563/4/042075.
Full text
20
Le Dréan, Y., P. H. Conze, M. Hatt, D. Visvikis, and B. Badic. "Segmentation automatique par DeepLearning en contexte de métastases hépatiques de cancer du côlon." Journal de Chirurgie Viscérale 158, no. 4 (August 2021): S64. http://dx.doi.org/10.1016/j.jchirv.2021.06.056.
Full text
21
Jaber, Mustafa I., Christopher W. Szeto, Bing Song, Liudmila Beziaeva, Stephen C. Benz, Patrick Soon-Shiong, and Shahrooz Rabizadeh. "Pathology image-based lung cancer subtyping using deeplearning features and cell-density maps." Electronic Imaging 2020, no. 10 (January 26, 2020): 64–1. http://dx.doi.org/10.2352/issn.2470-1173.2020.10.ipas-064.
Full textAbstract:
In this paper, we propose a patch-based system to classify non-small cell lung cancer (NSCLC) diagnostic whole slide images (WSIs) into two major histopathological subtypes: adenocarcinoma (LUAD) and squamous cell carcinoma (LUSC). Classifying patients accurately is important for prognosis and therapy decisions. The proposed system was trained and tested on 876 subtyped NSCLC gigapixel-resolution diagnostic WSIs from 805 patients – 664 in the training set and 141 in the test set. The algorithm has modules for: 1) auto-generated tumor/non-tumor masking using a trained residual neural network (ResNet34), 2) cell-density map generation (based on color deconvolution, local drain segmentation, and watershed transformation), 3) patch-level feature extraction using a pre-trained ResNet34, 4) a tower of linear SVMs for different cell ranges, and 5) a majority voting module for aggregating subtype predictions in unseen testing WSIs. The proposed system was trained and tested on several WSI magnifications ranging from x4 to x40 with a best ROC AUC of 0.95 and an accuracy of 0.86 in test samples. This fully-automated histopathology subtyping method outperforms similar published state-of-the-art methods for diagnostic WSIs.
22
Kwak, NaeJoung, and DongJu Kim. "Detection of Worker’s Safety Helmet and Mask and Identification of Worker Using Deeplearning." Computers, Materials & Continua 75, no. 1 (2023): 1671–86. http://dx.doi.org/10.32604/cmc.2023.035762.
Full text
23
Prastika, Indah Widhi, and Eri Zuliarso. "DETEKSI PENYAKIT KULIT WAJAH MENGGUNAKAN TENSORFLOW DENGAN METODE CONVOLUTIONAL NEURAL NETWORK." Jurnal Manajemen Informatika dan Sistem Informasi 4, no. 2 (October 29, 2021): 84–91. http://dx.doi.org/10.36595/misi.v4i2.418.
Full textAbstract:
Abstrak
Masyarakat Indonesia dengan kondisi yang berbeda khususnya kulit pada wajah. Hal tersebut menyebabkan beberapa penyakit yang dapat menyerang kulit wajah. Di Indonesia, banyak wanita yang menderita penyakit kulit, hal ini dibuktikan dari profil kesehatan Indonesia tahun 2015. Masyarakat banyak yang belum mengetahui penyakit kulit dan bahaya penyakit kulit akibat keterlambatan dalam penanganan. Penelitian ini akan mendeteksi penyakit kuit wajah secara real-time, lalu sistem ini akan mengklasifikasikan penyakit kulit yang ada di wajah. Tipe jaringan saraf yang disebut Convolutional Neural Network (CNN) cocok untuk tugas berhubungan gambar. Jaringan dilatih untuk mencari fitur, seperti tepi, sudut dan perbedaan warna, diseluruh gambar dan menggabungkannya menjadi bentuk yang kompleks. Aplikasi ini hanya dapat digunakan pada android sehingga menjalankan sistem secara real-time. Hasil yang didapat menunjukkan hasil yang cukup baik dengan menggunakan metode deep learning.
Kata kunci: Convolutional Neural Network (CNN), Penyakit Kulit, TensorFlow, DeepLearning, Sistem Deteksi
Abstract
Indonesian people have different skin conditions, especially the skin on the face. This one causes several diseases that can attack facial skin. Indonesia's 2015 health profile shows that many women suffer from skin diseases. Many people do not know about skin diseases and the dangers caused by delays in handling. This study will detect facial skin disease in real-time, then this system will classify skin diseases on the face. A type of neural network called a Convolutional Neural Network (CNN) is suitable for image-related tasks. The system is regular to look for features, such as edges, angles, and color differences across images and combine them into complex shapes. This application only on android, so it runs the system in real-time. The results obtained show passably results using the deep learning method.
Keywords: Convolutional Neural Network (CNN), Penyakit Kulit, TensorFlow, DeepLearning, Sistem Deteksi
24
Rikendry, Rikendry, and Azzin Maharil. "PERBANDINGAN ARSITEKTUR VGG16 DAN RESNET50 UNTUK REKOGNISI TULISAN TANGAN AKSARA LAMPUNG." Jurnal Informatika dan Rekayasa Perangkat Lunak 3, no. 2 (October 7, 2022): 236–43. http://dx.doi.org/10.33365/jatika.v3i2.2030.
Full textAbstract:
Pengenalan tulisan tangan atau biasa disebut Hand Writing Recognition (HWR)adalahsebuah sistem komputer yang dapat digunakan untuk mengenali huruf yangberasal dari tulisan tangan. HWR sendiri merupakan sistem yang dikembangkandari Optical Character Recognition (OCR), dengan adanya sistem HWR inidiharapkan komputer dapat membaca dan mengenali huruf-huruf ataupun karakteryang dimasukkan oleh user dalam bentuk tulisan tangan. Data yang digunakan padapenelitian ini berupa data gambar tulisan tangan aksara lampung sebanyak 20 aksara. Pada penelitian kali ini penulis akan membandingkan dua model deeplearning yaitu VGG16 dan ResNet50. Hasil dari penelitian ini menunjukan bahwamodel arsitektur VGG16 memberikan hasil akurasi 91% serta waktu training yanglebih baik, sedangkan untuk ResNet50 memberikan hasil akurasi sebesar 65% danmemerlukan waktu komputasi yang lebih lama dan hasil akurasi yang kecil
25
Gaddam, Abhishek. "Application Development for Mask Detection using Raspberry Pi." International Journal for Research in Applied Science and Engineering Technology 9, no. 9 (September 30, 2021): 1638–42. http://dx.doi.org/10.22214/ijraset.2021.38211.
Full textAbstract:
Abstract: In our daily life, humans are discovering new technology, and scientists also discovering new viruses. In recently scientists are discovered COVID-19 (coronavirus). COVID-19 pandemic has apace affected our everyday life-disrupting world trade and movements. Carrying a protecting mask has become a brand new tradition. Our planned technique detects the face from the video properly then it identifies if it's a mask wear on that or not. This project aims to develop a face mask detection system to detect any kind of face mask. The current study used OpenCV, Python, and Tensor Flow to detect whether a person wearing a face mask or not. The model was tested with real-time video streams. Keywords: Face mask detection, Face detection, mask detection, coronavirus, OpenCV, Tensorflow, Deeplearning
26
Ma, Y., F. Zhou, G. Wen, H. Gen, R. Huang, Q. Wu, and L. Pei. "A 3D LIDAR RECONSTRUCTION APPROACH FOR VEGETATION DETECTION IN POWER TRANSMISSION NETWORKS." International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLVI-3/W1-2022 (April 22, 2022): 141–48. http://dx.doi.org/10.5194/isprs-archives-xlvi-3-w1-2022-141-2022.
Full textAbstract:
Abstract. Vegetation management is important to the power transmission and distribution networks. The encompassed towering tree is always the key factor of the high impedance faults(HIFs).LiDAR is an efficient way to detect trees with 3D point cloud. The classical tree detection algorithm can handle the tree with high and distinct trunk,but limited to the tree with messy trunks. While the deeplearning based detection algorithms are also suffered from the terrain noise points. In this paper, we propose an efficient LiDAR reconstruction system which can efficiently reconstruct the point cloud of surrounding vegetation without the ground plane noise. We also use different weight strategies to improve the localization accuracy. We have conducted our system on the real power network environment and the height detection result shows that our algorithm has a better accuracy and robustness compared with the classical methods.
27
Kalaiselvi, Dr K. "Covid 19 Detection Using Deep Learning and Covid 19 Symptoms Checker." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 07, no. 12 (December 30, 2023): 1–10. http://dx.doi.org/10.55041/ijsrem27783.
Full textAbstract:
Abstract--The goal of this project is to classify healthy individuals, COVID-19 cases, and viral pneumonia cases. Deep learning is a type of machine learning. It enables us to teach artificial intelligence to anticipate outcomes given a set of data.Artificial intelligence can be trained through supervised learning. Voice and facial recognition, disease diagnosis, defence, and security are all domains where deep learning is applied. Artificial neuralnetworks are represented by the word deep in deep learning. The human brain inspired artificial neural networks. It is made up of neurons, just like the human brain. The amount and speed of learning are the main differences between them. To put it another way, artificial neural networks require data and processing capacity to be trained. The quality of machine learning methods is determined by the algorithms used. KEYWORDS: COVID-19, Privacy Preserved DataSharing, deeplearning, Symptoms checker
28
Rosa, Nicholas, Christopher J. Watkins, and Janet Newman. "Moving beyond MARCO." PLOS ONE 18, no. 3 (March 24, 2023): e0283124. http://dx.doi.org/10.1371/journal.pone.0283124.
Full textAbstract:
The use of imaging systems in protein crystallisation means that the experimental setups no longer require manual inspection to determine the outcome of the trials. However, it leads to the problem of how best to find images which contain useful information about the crystallisation experiments. The adoption of a deeplearning approach in 2018 enabled a four-class machine classification system of the images to exceed human accuracy for the first time. Underpinning this was the creation of a labelled training set which came from a consortium of several different laboratories. The MARCO classification model does not have the same accuracy on local data as it does on images from the original test set; this can be somewhat mitigated by retraining the ML model and including local images. We have characterized the image data used in the original MARCO model, and performed extensive experiments to identify training settings most likely to enhance the local performance of a MARCO-dataset based ML classification model.
29
Sharma, Udita, Neeraj Kumar, and Shafalii Sharma. "Deep Learning for Brain MRI Segmentation." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 07, no. 11 (November 1, 2023): 1–11. http://dx.doi.org/10.55041/ijsrem27209.
Full textAbstract:
Brain magnetic resonance imaging (MRI) plays a central role in this setting, providing detailed anatomical information for clinical evaluation. Segmentation of her MRI images of the brain is an essential step to obtaining meaningful information for diagnostic and therapeutic purposes. Deep learning, especially convolutional neural networks (CNN), has emerged as a powerful solution to automate brain MRI segmentation and improve accuracy. In particular, convolutional neural networks have demonstrated remarkable performance in segmenting brain structures such as gray matter, white matter, and cerebrospinal fluid, as well as detecting abnormalities such as tumors and lesions. The purpose of this article is to provide an overview of current deep learning-based segmentation approaches for quantitative brain MRI. First, we review current deeplearning architectures used to segment anatomical brain structures and lesions. Next, we summarize and discuss the performance, speed, and characteristics of deep learning approaches. Finally, it critically assesses the current situation and points out possible future developments and trends. Keywords—Deep Learning, Convolutional Neural Networks, Brain MRI.
30
Fonda, Hendry. "KLASIFIKASI BATIK RIAU DENGAN MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORKS (CNN)." Jurnal Ilmu Komputer 9, no. 1 (May 21, 2020): 7–10. http://dx.doi.org/10.33060/jik/2020/vol9.iss1.144.
Full textAbstract:
ABSTRACT
Riau batik is known since the 18th century and is used by royal kings. Riau Batik is made by using a stamp that is mixed with coloring and then printed on fabric. The fabric used is usually silk. As its development, comparing Javanese batik with riau batik Riau is very slowly accepted by the public. Convolutional Neural Networks (CNN) is a combination of artificial neural networks and deeplearning methods. CNN consists of one or more convolutional layers, often with a subsampling layer followed by one or more fully connected layers as a standard neural network. In the process, CNN will conduct training and testing of Riau batik so that a collection of batik models that have been classified based on the characteristics that exist in Riau batik can be determined so that images are Riau batik and non-Riau batik. Classification using CNN produces Riau batik and not Riau batik with an accuracy of 65%. Accuracy of 65% is due to basically many of the same motifs between batik and other batik with the difference lies in the color of the absorption in the batik riau.
Kata kunci: Batik; Batik Riau; CNN; Image; Deep Learning
ABSTRAK
Batik Riau dikenal sejak abad ke 18 dan digunakan oleh bangsawan raja. Batik Riau dibuat dengan menggunakan cap yang dicampur dengan pewarna kemudian dicetak di kain. Kain yang digunakan biasanya sutra. Seiring perkembangannya, dibandingkan batik Jawa maka batik Riau sangat lambat diterima oleh masyarakat. Convolutional Neural Networks (CNN) merupakan kombinasi dari jaringan syaraf tiruan dan metode deeplearning. CNN terdiri dari satu atau lebih lapisan konvolutional, seringnya dengan suatu lapisan subsampling yang diikuti oleh satu atau lebih lapisan yang terhubung penuh sebagai standar jaringan syaraf. Dalam prosesnya CNN akan melakukan training dan testing terhadap batik Riau sehingga didapat kumpulan model batik yang telah terklasi fikasi berdasarkan ciri khas yang ada pada batik Riau sehingga dapat ditentukan gambar (image) yang merupakan batik Riau dan yang bukan merupakan batik Riau. Klasifikasi menggunakan CNN menghasilkan batik riau dan bukan batik riau dengan akurasi 65%. Akurasi 65% disebabkan pada dasarnya banyak motif yang sama antara batik riau dengan batik lainnya dengan perbedaan terletak pada warna cerap pada batik riau.
Kata kunci: Batik; Batik Riau; CNN; Image; Deep Learning
31
Adamopoulos, Panagiotis, Anindya Ghose, and Alexander Tuzhilin. "Heterogeneous Demand Effects of Recommendation Strategies in a Mobile Application: Evidence from Econometric Models and Machine-Learning Instruments." MIS Quarterly 46, no. 1 (February 15, 2022): 101–50. http://dx.doi.org/10.25300/misq/2021/15611.
Full textAbstract:
In this paper, we examine the effectiveness of various recommendation strategies in the mobile channel and their impact on consumers’ utility and demand levels for individual products. We find significant differences in effectiveness among various recommendation strategies. Interestingly, recommendation strategies that directly embed social proofs for the recommended alternatives outperform other recommendations. In addition, recommendation strategies combining social proofs with higher levels of induced awareness due to the prescribed temporal diversity have an even stronger effect on the mobile channel. We also examine the heterogeneity of the demand effect across items, users, and contextual settings, further verifying empirically the aforementioned information and persuasion mechanisms and generating rich insights. We also facilitate the estimation of causal effects in the presence of endogeneity using machine-learning methods. Specifically, we develop novel econometric instruments that capture product differentiation (isolation) based on deeplearning models of user-generated reviews. Our empirical findings extend the current knowledge regarding the heterogeneous impact of recommender systems, reconcile contradictory prior results in the related literature, and have significant business implications.
32
Hatami, Muhammad, Tukino Tukino, Fitria Nurapriani, Widiyawati Widiyawati, and Wresti Andriani. "DETEKSI HELMET DAN VEST KESELAMATAN SECARA REALTIME MENGGUNAKAN METODE YOLO BERBASIS WEB FLASK." EDUSAINTEK: Jurnal Pendidikan, Sains dan Teknologi 10, no. 1 (January 10, 2023): 221–33. http://dx.doi.org/10.47668/edusaintek.v10i1.651.
Full textAbstract:
Menurut ILO, setiap tahun ada lebih dari 250 juta kecelakaan di tempat kerja. Penyebab kecelakaan sebanyak 80% dikarenakan kelalaian yang dilakukan oleh pekerja yaitu perilaku tidak aman seperti tidak memakai APD. Perlunya pengawasan terhadap pekerja merupakan hal penting dalam mengurangi kecelakaan kerja. Namun pengawasan tersebut masih manual, sehingga akan memakan waktu lama. Metode yang dapat digunakan untuk pengenalan objek pada citra helmet dan vest keselamatan adalah deeplearning. YOLOv2 merupakan salah satu model deep learning yang dapat digunakan untuk pengenalan objek. Mengingatnya permasalahan tersebut, maka perlu dibuat sistem deteksi helmet dan vest secara realtime berbasis web flask. Tahapan pada penelitian ini diantara lain data acquisition atau pengumpulan data citra. selanjutnya data exprolation atau anotasi data citra, selanjutnya dilakukan Modelling atau training data, dan proses terakhir yaitu deployment menggunakan flask. sistem yang telah dibuat berhasil mendeteksi tidak menggunakan helmet dan vest keselamatan dengan bounding box merah dan menggunakan helmet dan vest keselamatan dengan bounding box hijau dengan akurasi rata rata 81.60% dan memiliki nilai avg loss 0.173 dan nilai validasi mAP (mean Average Precision) 76.68%
33
Habbat, Nassera, Hicham Nouri, Houda Anoun, and Larbi Hassouni. "Using AraGPT and ensemble deep learning model for sentiment analysis on Arabic imbalanced dataset." ITM Web of Conferences 52 (2023): 02008. http://dx.doi.org/10.1051/itmconf/20235202008.
Full textAbstract:
With the fast growth of mobile technology, social media has become important for people to share their thoughts and feelings. Businesses and governments can make better strategic decisions when they know what the public thinks. Because of this, sentiment analysis is an important tool for figuring out how different people’s opinions are. This article presents a deeplearning ensemble model for sentiment analysis. The ensemble model proposed consists of three deep-learning models, Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BiLSTM), as base classifiers. AraBERT is responsible for presenting the textual input data into representative embeddings. The stacking ensemble model then captures the long-range dependencies in the embedding for a given class. As a meta-classifier, Support Vector Machine (SVM) then combines the predictions made by the stacking deep learning model. In addition, data augmentation with AraGPT was implemented to address the imbalanced dataset issues. The experimental results demonstrate that the proposed model outperforms the state-of-the-art models with an accuracy of 88.89%, 90.88%, and 88.23% on the HARD, BRAD, and Twitter datasets, respectively.
34
López Frías, Claudia. "Deepfakes, Seeing is Believing?" Postmodernism Problems 13, no. 3 (December 5, 2023): 294–306. http://dx.doi.org/10.46324/pmp2303294.
Full textAbstract:
Artificial intelligence has burst into our lives and today it is a constant in our routines. Initially, it represented a great advance in everything that until now limited the human being. It also seems to have a series of risks that we are only beginning to be aware of. One of the technologies derived from AI is that of deepfakes, words that arise as an acronym when combining Deep, coming from how these intelligences learn, through deeplearning, and fake, whose translation would be false or falsification. It is a technology widely used in audiovisuals, both for cinema, television, or other types of videos, with variable results. However, the use of pornography of celebrities without their consent, or the deliberate interest in misinforming, at critical moments, are some of the problems faced by the use of this technology. Something that seems to reach a critical point when it comes to news since the presenters usually enjoy greater credibility for the viewer. Throughout this work, we will try to approach the use of artificial intelligence on television as well as Deepfakes, their uses, and risks.
35
Ming, Yifei, Hang Yin, and Yixuan Li. "On the Impact of Spurious Correlation for Out-of-Distribution Detection." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 9 (June 28, 2022): 10051–59. http://dx.doi.org/10.1609/aaai.v36i9.21244.
Full textAbstract:
Modern neural networks can assign high confidence to inputs drawn from outside the training distribution, posing threats to models in real-world deployments. While much research attention has been placed on designing new out-of-distribution (OOD) detection methods, the precise definition of OOD is often left in vagueness and falls short of the desired notion of OOD in reality. In this paper, we present a new formalization and model the data shifts by taking into account both the invariant and environmental (spurious) features. Under such formalization, we systematically investigate how spurious correlation in the training set impacts OOD detection. Our results suggest that the detection performance is severely worsened when the correlation between spurious features and labels is increased in the training set. We further show insights on detection methods that are more effective in reducing the impact of spurious correlation, and provide theoretical analysis on why reliance on environmental features leads to high OOD detection error. Our work aims to facilitate better understanding of OOD samples and their formalization, as well as the exploration of methods that enhance OOD detection. Code is available at https://github.com/deeplearning-wisc/Spurious_OOD.
36
Hou, Yue, Xin Zheng, Chengyan Han, Wei Wei, Rafał Scherer, and Dawid Połap. "Deep Learning Methods in Short-Term Traffic Prediction: A Survey." Information Technology and Control 51, no. 1 (March 26, 2022): 139–57. http://dx.doi.org/10.5755/j01.itc.51.1.29947.
Full textAbstract:
Nowadays, traffic congestion has become a serious problem that plagues the development of many cities aroundthe world and the travel and life of urban residents. Compared with the costly and long implementation cyclemeasures such as the promotion of public transportation construction, vehicle restriction, road reconstruction, etc., traffic prediction is the lowest cost and best means to solve traffic congestion. Relevant departmentscan give early warnings on congested road sections based on the results of traffic prediction, rationalize thedistribution of police forces, and solve the traffic congestion problem. At the same time, due to the increasingreal-time requirements of current traffic prediction, short-term traffic prediction has become a subject of widespread concern and research. Currently, the most widely used model for short-term traffic prediction are deeplearning models. This survey studied the relevant literature on the use of deep learning models to solve shortterm traffic prediction problem in the top journals of transportation in recent years, summarized the currentcommonly used traffic datasets, the mainstream deep learning models and their applications in this field. Finally, the challenges and future development trends of deep learning models applied in this field are discussed.
37
Polyakov, Evrenii, Leonid Voskov, Pavel Abramov, and Sergey Polyakov. "Generalized approach to sentiment analysis of short text messages in natural language processing." Information and Control Systems, no. 1 (February 20, 2020): 2–14. http://dx.doi.org/10.31799/1684-8853-2020-1-2-14.
Full textAbstract:
Introduction: Sentiment analysis is a complex problem whose solution essentially depends on the context, field of study andamount of text data. Analysis of publications shows that the authors often do not use the full range of possible data transformationsand their combinations. Only a part of the transformations is used, limiting the ways to develop high-quality classification models.Purpose: Developing and exploring a generalized approach to building a model, which consists in sequentially passing throughthe stages of exploratory data analysis, obtaining a basic solution, vectorization, preprocessing, hyperparameter optimization, andmodeling. Results: Comparative experiments conducted using a generalized approach for classical machine learning and deeplearning algorithms in order to solve the problem of sentiment analysis of short text messages in natural language processinghave demonstrated that the classification quality grows from one stage to another. For classical algorithms, such an increasein quality was insignificant, but for deep learning, it was 8% on average at each stage. Additional studies have shown that theuse of automatic machine learning which uses classical classification algorithms is comparable in quality to manual modeldevelopment; however, it takes much longer. The use of transfer learning has a small but positive effect on the classificationquality. Practical relevance: The proposed sequential approach can significantly improve the quality of models under developmentin natural language processing problems.
38
Azha Javed and Muhammad Javed Iqbal. "Classification of Biological Data using Deep Learning Technique." NUML International Journal of Engineering and Computing 1, no. 1 (April 27, 2022): 13–26. http://dx.doi.org/10.52015/nijec.v1i1.10.
Full textAbstract:
A huge amount of newly sequenced proteins is being discovered on daily basis. The mainconcern is how to extract the useful characteristics of sequences as the input features for thenetwork. These sequences are increasing exponentially over the decades. However, it is veryexpensive to characterize functions for biological experiments and also, it is really necessaryto find the association between the information of datasets to create and improve medicaltools. Recently machine learning algorithms got huge attention and are widely used. Thesealgorithms are based on deep learning architecture and data-driven models. Previous workfailed to properly address issues related to the classification of biological sequences i.e.protein including efficient encoding of variable length biological sequence data andimplementation of deep learning based neural network models to enhance the performance ofclassification/ recognition systems. To overcome these issues, we have proposed a deeplearning based neural network architecture so that classification performance of the systemcan be increased. In our work, we have proposed 1D-convolution neural network whichclassifies the protein sequences to 10 top common classes. The model extracted features fromthe protein sequences labels and learned through the dataset. We have trained and evaluateour model on protein sequences downloaded from protein data bank (PDB). The modelmaximizes the accuracy rate up to 96%.
39
Shaheer, Rizana, and Malu U. "Real-Time Video Violence Detection Using CNN." International Journal for Research in Applied Science and Engineering Technology 11, no. 5 (May 31, 2023): 2586–90. http://dx.doi.org/10.22214/ijraset.2023.52182.
Full textAbstract:
Abstract: In order to effectively enforce the law and keep cities secure, monitoring technologies that detect violent events are becoming increasingly important. In computer vision, the practice of action recognition has gained popularity. In the field of computer vision, action recognition has gained popularity. The action recognition group, however, has mainly concentrated on straightforward activities like clapping, walking, jogging, etc. Comparatively little study has been done on identifying specific occurrences that have immediate practical applications, like fighting or violent behaviors in general. The responsiveness, precision, and flexibility of violent event detectors are indicators of their effectiveness across a range of video sources. This capacity might be helpful in specific video surveillance situations. Several research focused on violence identification with an emphasis on speed, accuracy, or both while ignoring the generalizability of various video source types. In this paper, a deeplearning-based real-time violence detector has been proposed. CNN serves as an extractor of spatial features in the suggested model. Here, a convolutional neural network (CNN) architecture called MobileNet V2 is utilized to extract frame-level information from a video, and LSTM, which focuses on the three factors (overall generality, accuracy, and quick reaction) as a temporal relation learning approach.
40
R, Arun Sekar. "Novel Pollination Drone for Agricultural Assistance." International Journal for Research in Applied Science and Engineering Technology 10, no. 6 (June 30, 2022): 3408–20. http://dx.doi.org/10.22214/ijraset.2022.44596.
Full textAbstract:
Abstract: One of the major issues concerning current agricultural productionis crop pollination. Approximately $74 billion per year worth of crops in rely on pollination by various pollinators. However, the recent decline ofhoney bees (i.e. colony collapse disorder) has greatly threatened productivity. Declines of other native pollinators, such as different insecttypes and animals, have also been reported. Such shortages of pollinatorshave significantly increased the cost of farmers and renting them for pollination services. To overcome this problem, this project presents an automated drone for pollination which uses deeplearning and machine learning algorithms to estimate the flower position, size, orientation, andphysical condition to guide the drone to capture and interact with flowersfor pollination. In this concept we use drone and artificial intelligence method to carry pre collected pollen and to inject them in flowers for pollination to increase productivity. Drone pollination bypasses many current issues with natural pollinators inagriculture, such as honeybee colony collapse disorder, pollinator parasites and diseases, predators, pesticide spray, adverse weather, and the availability of pollinators in a timely manner. Second, robotic pollinators will improve fruit quality andproduction. With the decreasing number of bees, artificial pollination is more in trend. If we take the example of China, 100% plants are pollinated artificially. So, we can see that artificial pollination is beneficial and can increase plant productivity. The successful completionof this project will significantly impact the field of artificial pollination inagriculture.
41
Chung, Junho, Sangkyoo Park, Dongsung Pae, Hyunduck Choi, and Myotaeg Lim. "Feature-Selection-Based Attentional-Deconvolution Detector for German Traffic Sign Detection Benchmark." Electronics 12, no. 3 (February 1, 2023): 725. http://dx.doi.org/10.3390/electronics12030725.
Full textAbstract:
In this study, we propose a novel traffic sign detection algorithm based on the deeplearning approach. The proposed algorithm, which we termed the feature-selection-based attentionaldeconvolution detector (FSADD), is used along with the “you look only once” (YOLO) v5 structure for feature selection. When applying feature selection inside a detection algorithm, the network divides the extracted feature maps after the convolution layer into similar and non similar feature maps. Generally, the feature maps obtained after the convolution layers are the outputs of filters with random weights. Owing to the randomness of the filter, the network obtains various kinds of feature maps with unnecessary components, which degrades the detection performance. However, grouping feature maps with high similarities can increase the relativeness of each feature map, thereby improving the network detection of specific targets from images. Furthermore, the proposed FSADD model has modified sizes of the receptive fields for improved traffic sign detection performance. Many of the available general detection algorithms are unsuitable for the German traffic sign detection benchmark (GTSDB) because of the small sizes of these signs in the images. Experimental comparisons were performed with respect to the GTSDB to show that the proposed FSADD is comparable to the state-of-the-art while detecting 29 kinds of traffic signs with 73.9% accuracy of classification performances.
42
Alagu, Prakalya P., and Gaud Nirmal. "BiDETECT: BiLSTM with BERT for hate speech detection in tweets." i-manager's Journal on Computer Science 10, no. 4 (2023): 23. http://dx.doi.org/10.26634/jcom.10.4.19334.
Full textAbstract:
The utilization of online platforms for spreading hate speech has become a major concern. The conventional techniques used to identify hate speech, such as relying on keywords and manual moderation, frequently fall short and can lead to either missed detections or incorrect identifications. In response, researchers have developed various deeplearning strategies for locating hate speech in text. This paper covers a wide range of Deep Learning approaches, encompassing Convolutional Neural Networks and especially transformer-based models. It also discusses the key factors that influence the performance of these methods, such as the choice of datasets, the use of pre-processing strategies, and the design of the model architecture. In conjunction with summarizing existing research, it also identifies a selection of key hurdles and limitations of Deep Learning for discovering hate speech and has proposed a novel method to overcome them. In Bidirectional Long Short-Term Memory and BERT for Hate Speech Detection (BiDETECT), which involves adding a Bidirectional Long Short-Term Memory (BiLSTM) layer to Bidirectional Encoder Representations from Transformers (BERT) for classification, the hurdles include the difficulties in defining hate speech, the limitations of current datasets, and the challenges of generalizing models to new domains. It also discusses the ethical implications of employing Deep Learning to pinpoint hate speech and the need for responsible and transparent research in this area.
43
Çetiner, Halit, and Sedat Metlek. "Classification of Weather Phenomenon with a New Deep Learning Method Based on Transfer Learning." International Conference on Recent Academic Studies 1 (May 12, 2023): 92–99. http://dx.doi.org/10.59287/icras.678.
Full textAbstract:
Recognition of weather conditions, which have an important effect on the planning of our dailylives, affects many events from transport to agriculture. Even on an ordinary day, the weather affects manyevents, from taking children to the market to taking a walk. In addition, in many commercial areas such asagriculture and animal husbandry, many issues from planting and planting time to production are directlyor indirectly related to weather conditions. For these reasons, automatic analyses and classification of aerialimages will provide significant convenience. New technologies based on deep learning are needed tominimize the errors of experts working in the towers established to monitor weather conditions. Deeplearning based systems are preferred because they bring a new perspective to feature extraction andclassification approaches in classical machine learning technologies. With deep learning based systems, itis possible to classify by obtaining distinctive features from different weather conditions. In this paper, apre-trained architecture-based deep learning model is proposed to classify a dataset containing 6877 imagesof 11 weather conditions. In order to measure the effect of the proposed model on the performance, acomparison with the basic model is performed. The weather classification accuracy of the proposed modelin the test set is 88%. This performance result shows that the model is competitive with its competitors. Atthis point, eleven different weather images can be automatically classified. As a result of the mentionedprocedures, this study can be a reference for future weather classification studies.
44
Elbasir, Abdurrahman, Balasubramanian Moovarkumudalvan, Khalid Kunji, Prasanna R. Kolatkar, Raghvendra Mall, and Halima Bensmail. "DeepCrystal: a deep learning framework for sequence-based protein crystallization prediction." Bioinformatics 35, no. 13 (November 21, 2018): 2216–25. http://dx.doi.org/10.1093/bioinformatics/bty953.
Full textAbstract:
Abstract Motivation Protein structure determination has primarily been performed using X-ray crystallography. To overcome the expensive cost, high attrition rate and series of trial-and-error settings, many in-silico methods have been developed to predict crystallization propensities of proteins based on their sequences. However, the majority of these methods build their predictors by extracting features from protein sequences, which is computationally expensive and can explode the feature space. We propose DeepCrystal, a deep learning framework for sequence-based protein crystallization prediction. It uses deep learning to identify proteins which can produce diffraction-quality crystals without the need to manually engineer additional biochemical and structural features from sequence. Our model is based on convolutional neural networks, which can exploit frequently occurring k-mers and sets of k-mers from the protein sequences to distinguish proteins that will result in diffraction-quality crystals from those that will not. Results Our model surpasses previous sequence-based protein crystallization predictors in terms of recall, F-score, accuracy and Matthew’s correlation coefficient (MCC) on three independent test sets. DeepCrystal achieves an average improvement of 1.4, 12.1% in recall, when compared to its closest competitors, Crysalis II and Crysf, respectively. In addition, DeepCrystal attains an average improvement of 2.1, 6.0% for F-score, 1.9, 3.9% for accuracy and 3.8, 7.0% for MCC w.r.t. Crysalis II and Crysf on independent test sets. Availability and implementation The standalone source code and models are available at https://github.com/elbasir/DeepCrystal and a web-server is also available at https://deeplearning-protein.qcri.org. Supplementary information Supplementary data are available at Bioinformatics online.
45
Shabbeer Ahmad, Syed, and Shreyas Jagadeep Shete. "nnovative Deep Learning-Based Medical Report Analysis for Timely Diagnosis and Improved Healthcare." Sparklinglight Transactions on Artificial Intelligence and Quantum Computing 02, no. 02 (2022): 16–28. http://dx.doi.org/10.55011/staiqc.2022.2203.
Full textAbstract:
In contemporary healthcare, a novel web-based platform harnessing the power of deep learning has been innovated to support frontline medical staff during critical emergencies, especially in the absence of expert consultation. This system is primed to swiftly analyze medical records, emphasizing early detection to curtail severe health risks, including potential fatalities. The foundation of this tool is rooted in deeplearning algorithms, which sift through vast medical data, revealing patterns often overlooked by human eyes. By augmenting precise disease identification, the system strengthens decision-making in clinical settings. Its design fosters synergy between the healthcare sector and specialized bodies, ensuring its adaptability to the evolving medical landscape. This fusion of artificial intelligence empowers healthcare practitioners by highlighting immediate risks, enriching patient care efficiency, and integrating fluidly with prevailing operational protocols. Thetool's proficiency in real-time anomaly detection aids clinicians in proactive decision-making, minimizing catastrophic health outcomes. Its pioneering application has demonstrated efficacy in early diagnostic evaluations for a spectrum of six predominantailments, encapsulating succinct insights for each. With an emphasis on processing medical images, including X-rays, the deep learning models display exemplary performance in training and diagnostics. The system, crafted with streamlit,is intuitively designed for emergency scenarios and is fortified for scalability through Docker containerization and cloud hosting. While this initiative underscores the transformative potential of deep learning in health analytics, it heralds the dawn of an era where medical verdicts become more pinpointed, timely, and instrumental in preserving life.© 2022 STAIQC. All rights reserved
46
Jain, Vinesh Kumar, Arka Prokash Mazumdar, and Mahesh Chandra Govil. "Congestion Prediction in Internet of Things Network using Temporal Convolutional Network A Centralized Approach." Defence Science Journal 72, no. 6 (December 6, 2022): 810–23. http://dx.doi.org/10.14429/dsj.72.17447.
Full textAbstract:
The unprecedented ballooning of network traffic flow, specifically, Internet of Things (IoT) network traffic, has big stressed of congestion on todays Internet. Non-recurring network traffic flow may be caused by temporary disruptions, such as packet drop, poor quality of services, delay, etc. Hence, the network traffic flow estimation is important in IoT networks to predict congestion. As the data in IoT networks is collected from a large number of diversified devices which have unlike format of data and also manifest complex correlations, so the generated data is heterogeneous and nonlinear in nature. Conventional machine learning approaches unable to deal with nonlinear datasets and suffer from misclassification of real network traffic due to overfitting. Therefore, it also becomes really hard for conventional machine learning tools like shallow neural networks to predict the congestion accurately. Accuracy of congestion prediction algorithms play an important role to control the congestion by regulating the send rate of the source. Various deeplearning methods (LSTM, CNN, GRU, etc.) are considered in designing network traffic flow predictors, which have shown promising results. In this work, we propose a novel congestion predictor for IoT, that uses Temporal Convolutional Network (TCN). Furthermore, we use Taguchi method to optimize the TCN model that reduces the number of runs of the experiments. We compare TCN with other four deep learning-based models concerning Mean Absolute Error (MAE) and Mean Relative Error (MRE). The experimental results show that TCN based deep learning framework achieves improved performance with 95.52% accuracy in predicting network congestion. Further, we design the Home IoT network testbed to capture the real network traffic flows as no standard dataset is available.
47
Morales Sanabria, Carmen, and Blanca San-José Montano. "Actualízate celebra su novena edición bajo el título El valor holístico del profesional de la información." CLIP de SEDIC: Revista de la Sociedad Española de Documentación e Información Científica, no. 85 (June 14, 2022): 60–67. http://dx.doi.org/10.47251/clip.n85.79.
Full textAbstract:
La novena Jornada de Actualízate se ha celebrado bajo el título El valor holístico del profesional de la información, con objeto de destacar los principios de interdependencia, diversidad y sostenibilidad de la disciplina en el marco de la gestión integral de la información.
En la primera mesa, El valor holístico de la sociedad del conocimiento, se ha resaltado el valor de los profesionales que gestionan información por su labor en la conservación, preservación y organización del conocimiento, así como por su capacidad para analizar, sintetizar y catalogar la información a fin de facilitar su acceso. También se ha hablado de las bibliotecas como hogares para la ciudadanía, en la medida que construyen comunidad y son espacios habitables, heterogéneos, organizados y ordenados, centros de sabiduría y de conocimiento.
En la segunda mesa, Evolución en el procesamiento automatizado de la información, se ha mostrado la incorporación de las nuevas tecnologías en el procesamiento de la información, poniéndose el foco en el uso de redes neuronales para la clasificación automática, en el procesamiento del lenguaje natural y en las últimas tendencias, como deeplearning, blockchain y word embeddings. El uso de blockchain tiene importantes implicaciones sociológicas por lo que es fundamental la aplicación de la filosofía, antropología y sociología para las máquinas y las personas que trabajan con ellas.
En la tercera mesa, Tendencias en la difusión de la información, se ha analizado el esfuerzo de las organizaciones y administraciones públicas por crear diferentes contenidos, con diversos lenguajes y espacios -webs, vídeos o infografías-, que implican una profesionalización. Asimismo, se ha incidido en la credibilidad de la información sometida a procesos de verificación consistentes y en la responsabilidad compartida con la audiencia, creándose, de este modo, un acercamiento e implicación del usuario para formar comunidad.
48
Yin, Bojian, Marleen Balvert, Rick A. A. van der Spek, Bas E. Dutilh, Sander Bohté, Jan Veldink, and Alexander Schönhuth. "Using the structure of genome data in the design of deep neural networks for predicting amyotrophic lateral sclerosis from genotype." Bioinformatics 35, no. 14 (July 2019): i538—i547. http://dx.doi.org/10.1093/bioinformatics/btz369.
Full textAbstract:
Abstract Motivation Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disease caused by aberrations in the genome. While several disease-causing variants have been identified, a major part of heritability remains unexplained. ALS is believed to have a complex genetic basis where non-additive combinations of variants constitute disease, which cannot be picked up using the linear models employed in classical genotype–phenotype association studies. Deep learning on the other hand is highly promising for identifying such complex relations. We therefore developed a deep-learning based approach for the classification of ALS patients versus healthy individuals from the Dutch cohort of the Project MinE dataset. Based on recent insight that regulatory regions harbor the majority of disease-associated variants, we employ a two-step approach: first promoter regions that are likely associated to ALS are identified, and second individuals are classified based on their genotype in the selected genomic regions. Both steps employ a deep convolutional neural network. The network architecture accounts for the structure of genome data by applying convolution only to parts of the data where this makes sense from a genomics perspective. Results Our approach identifies potentially ALS-associated promoter regions, and generally outperforms other classification methods. Test results support the hypothesis that non-additive combinations of variants contribute to ALS. Architectures and protocols developed are tailored toward processing population-scale, whole-genome data. We consider this a relevant first step toward deep learning assisted genotype–phenotype association in whole genome-sized data. Availability and implementation Our code will be available on Github, together with a synthetic dataset (https://github.com/byin-cwi/ALS-Deeplearning). The data used in this study is available to bona-fide researchers upon request. Supplementary information Supplementary data are available at Bioinformatics online.
49
Alfonso-Francia, Gendry, Jesus Carlos Pedraza-Ortega, Mariana Badillo-Fernández, Manuel Toledano-Ayala, Marco Antonio Aceves-Fernandez, Juvenal Rodriguez-Resendiz, Seok-Bum Ko, and Saul Tovar-Arriaga. "Performance Evaluation of Different Object Detection Models for the Segmentation of Optical Cups and Discs." Diagnostics 12, no. 12 (December 2, 2022): 3031. http://dx.doi.org/10.3390/diagnostics12123031.
Full textAbstract:
Glaucoma is an eye disease that gradually deteriorates vision. Much research focuses on extracting information from the optic disc and optic cup, the structure used for measuring the cup-to-disc ratio. These structures are commonly segmented with deeplearning techniques, primarily using Encoder–Decoder models, which are hard to train and time-consuming. Object detection models using convolutional neural networks can extract features from fundus retinal images with good precision. However, the superiority of one model over another for a specific task is still being determined. The main goal of our approach is to compare object detection model performance to automate segment cups and discs on fundus images. This study brings the novelty of seeing the behavior of different object detection models in the detection and segmentation of the disc and the optical cup (Mask R-CNN, MS R-CNN, CARAFE, Cascade Mask R-CNN, GCNet, SOLO, Point_Rend), evaluated on Retinal Fundus Images for Glaucoma Analysis (REFUGE), and G1020 datasets. Reported metrics were Average Precision (AP), F1-score, IoU, and AUCPR. Several models achieved the highest AP with a perfect 1.000 when the threshold for IoU was set up at 0.50 on REFUGE, and the lowest was Cascade Mask R-CNN with an AP of 0.997. On the G1020 dataset, the best model was Point_Rend with an AP of 0.956, and the worst was SOLO with 0.906. It was concluded that the methods reviewed achieved excellent performance with high precision and recall values, showing efficiency and effectiveness. The problem of how many images are needed was addressed with an initial value of 100, with excellent results. Data augmentation, multi-scale handling, and anchor box size brought improvements. The capability to translate knowledge from one database to another shows promising results too.
50
Yadlapalli, Priyanka, and Bhavana D. "Application of Fuzzy Deep Neural Networks for Covid 19 diagnosis through chest Radiographs." F1000Research 12 (January 16, 2023): 60. http://dx.doi.org/10.12688/f1000research.126197.1.
Full textAbstract:
Background: The increasing number of COVID-19 patients around the world and the limited number of detection kits pose a challenge in determining the presence of the disease. Imaging modalities such as X-rays are commonly used because they are readily available and cost-effective. Deep learning has proved to be an excellent tool because of the abundance of online medical images in various medical modalities, such as X-Ray, computerized tomography (CT) Scan, and magnetic resonance imaging (MRI). A large number of medical research projects have been proposed and launched since early 2020 due to the overwhelming use of deep learning techniques in medical imaging. Methods: We have used fuzzy logic and deep learning to determine if chest X-ray images belong to people who have pneumonia related to COVID-19 and people who have interstitial pneumonias that aren't related to COVID-19. Results: In comparison to the current literature, the proposed transfer learning approach is more successful. It is possible to classify covid, viral, and bacterial pneumonia or a healthy patient using ResNet 18 Architecture's four-class classifiers. The proposed method achieved a 97% classification accuracy, 96% precision, and 98% recall in the case of COVID-19 detection using chest X-ray images, which demonstrates the importance of deep learning in medical image diagnosis. Furthermore, the results demonstrate that the proposed technique has the maximum sensitivity rate, with 97.1% ratio. Finally, with a 97.47% F1-score rate, the proposed strategy yields the highest value when compared to the others. Conclusions: DeepLearning techniques and fuzzy features resulted in an improved classification ability, with an accuracy rate of up to 97.7% using ResNet 18, which is a better value when compared to the remaining techniques. Classification of COVID-19 scans and other pneumonia cases have been done successfully by demonstrating the potential for applying such deep learning techniques in the near future.